CVE-2026-55574
vllm-project vllm 취약점
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allo...
- 대응 우선순위
- 점검
- CVSS
- 8.7
- EPSS
- 0.32% 백분위 24.9% · 2026.07.28 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.07.07